PA-Net: Learning local features using by pose attention for short-term person re-identification

doi:10.1016/j.ins.2021.02.066

	PA-Net: Learning local features using by pose attention for short-term person re-identification
	Wang, Kai 3,4; Dong, Shichao 4; Liu, Nian 4; Yang, Junhui 4; Li, Tao 2,4; Hu, Qinghua 1
刊名	INFORMATION SCIENCES
	2021-07-01
卷号	565 页码:196-209
关键词	Person re-identification Pose attention Feature fusion Deep learning
ISSN号	0020-0255
DOI	10.1016/j.ins.2021.02.066
英文摘要	Person re-identification (Re-ID) is an important but challenging task in video surveillance applications. In Re-ID tasks, pose is an extremely useful cue to identify a person, even from the back view. Therefore, pose-detection models may learn the features that are beneficial to the Re-ID task and improve the Re-ID performance by fusing the feature maps into the Re-ID model. Two key problems in integrating the pose cues are addressed in this study. One is how to reduce the noise caused by cross-domain datasets. The other is how to fuse the feature maps to better utilize high-level semantic pose cues. To address these two key problems, we first propose PA-Net by combining the pose attention stream and the global attention stream, where the global attention stream distinguishes persons with different global appearances, and the pose attention stream distinguishes persons with similar global appearance but different poses. Then, we present a pose attention stream that learns local features to reduce the noise in the pose cues caused by the cross-domain datasets and provide more semantic information for the Re-ID task. The effects of the proposed pose attention are demonstrated in an ablation study, and comparative experiments show that PA-Net achieves state-of-the-art performance. (c) 2021 Elsevier Inc. All rights reserved.
资助项目	National Key Research and Development Program of China[2018YFB2100304] ; National Natural Science Foundation of China[61872200] ; National Natural Science Foundation of China[62002175] ; National Natural Science Foundation of China[61925602] ; National Natural Science Foundation of China[61732011] ; Open Project Fund of State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences[CARCH201905] ; Natural Science Foundation of Tianjin[19JCZDJC31600] ; Natural Science Foundation of Tianjin[18YFYZCG00060] ; CERNET Innovation Project[NGII20190402]
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER SCIENCE INC
WOS记录号	WOS:000653661400012
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/17556]
专题	中国科学院计算技术研究所
通讯作者	Li, Tao
作者单位	1.Tianjin Univ, Sch Artificial Intelligence, Tianjin, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, State Key Lab Comp Architecture, Beijing, Peoples R China 3.Key Lab Med Data Anal & Stat Res Tianjin, Tianjin, Peoples R China 4.Nankai Univ, Coll Comp Sci, Tianjin, Peoples R China
推荐引用方式 GB/T 7714	Wang, Kai,Dong, Shichao,Liu, Nian,et al. PA-Net: Learning local features using by pose attention for short-term person re-identification[J]. INFORMATION SCIENCES,2021,565:196-209.
APA	Wang, Kai,Dong, Shichao,Liu, Nian,Yang, Junhui,Li, Tao,&Hu, Qinghua.(2021).PA-Net: Learning local features using by pose attention for short-term person re-identification.INFORMATION SCIENCES,565,196-209.
MLA	Wang, Kai,et al."PA-Net: Learning local features using by pose attention for short-term person re-identification".INFORMATION SCIENCES 565(2021):196-209.